基于小波分解和人工神经网络的短期负荷预测

提出了一种基于小波分解和人工神经网络(ANN)的电力系统短期负荷预测方法.通过小波变换把负荷序列分解为不同频段的子序列,再对这些子序列分别采用相匹配的人工神经网络模型进行预测,最后综合得到负荷序列的最终预测结果.在所提出的方法中小波分解能够提取负荷的一些周期性和非线性特征,并对其进行进一步细分,根据其子序列各自所具有的规律采用相应的预测方法;而ANN对于处理非线性及无法显示明确规律的问题具有优势.经实例验证,与传统方法相比该方法具有很高的预测精度和较强的适应能力.

AN APPROACH TO SHORT-TERM LOAD FORECASTING BASED ON WAVELET TRANSFORM AND ARITFICIAL NEURAL NETWORK

A wavelet decomposition based new approach to short-time load forecasting by artificial neural network (ANN) based on wavelet decomposition is proposed. Through the wavelet transform the load sequence is decomposed into subsequences on different scales, then using appropriate artificial neural networks these sub-sequences are forecasted by appropriate artificial neural networks respectively, finally after the synthesis of the forecasted results from the sub-sequences the final forecasting result of the load sequence is obtained. In the proposed method the wavelet decomposition can extract some periodical and nonlinear features of the load and subdivide them further, thus corresponding forecasting method can be used according to the coexisting rules of the subsequences themselves respectively; and the ANN possesses superiority in the processing of the problems which is nonlinear or its rule cannot be determinately displayed. The calculation results of a practical example show that the proposed method possesses high forecasting accuracy and better adaptability than traditional forecasting methods.